IIIT Hyderabad Publications |
|||||||||
|
Sub-phonetic modeling for capturing pronunciation variations for conversational speech synthesisAuthors: Kishore Prahallad,Alan W Black,Ravishankar Mosur Conference: in Proceedings of IEEE Int. Conf. Acoust., Speech, and Signal Processing (ICASSP), France 2006. Date: 2007-07-18 Report no: IIIT/TR/2007/26 AbstractIn this paper we address the issue of pronunciation modeling for conversational speech synthesis. We experiment with two different HMM topologies (fully connected state model and forward connected state model) for sub-phonetic modeling to capture the deletion and insertion of sub-phonetic states during speech production process. We show that the experimented HMM topologies have higher log likelihood than the traditional 5-state sequential model. We also study the first and second mentions of content words and their influence on the pronunciation variation. Finally we report phone recognition experiments using the modified HMM topologies. Full paper: pdf Centre for Language Technologies Research Centre |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |